<?xml version="1.0" standalone="yes"?>
<Paper uid="W94-0315">
  <Title>Using a textual representational level component in the context of discourse or dialogue generation</Title>
  <Section position="3" start_page="0" end_page="128" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Traditionally, the architecture of a generation system is either pipelined (e.g., TEXT \[McKeown 85\]), interleaved (e.g., PAULINE \[Hovy 90\]) or integrate.d (e.g., KAMP \[Appelt 85\]). Whatever the approach, the system is divided into two main components: a message planning component and a linguistic realization component. The former is responsible for the selection and organization of the information to be conveyed; it builds a structure often called message. The latter involves the formulation of the message in grammatically correct sentences. In a context of discourse, the message planning component is a text planner and the message is a text plan *This work was realized at the lstituto per la Ricerca Scientifica e Tecnolo#ica (IRST) in Trento (Italy).</Paragraph>
    <Paragraph position="1"> (e.g., see \[Maier &amp; Not 93\]). In a context of dialogue, the message planner is a 'fictitious' component consisting of a dialogue act planner, which precedes the generation system, and a planner for surface linguistic acts, which is a component of the generation system. The dialogue act planner builds plans of dialogue acts. A plan of dialogue acts is a tree-like structure in which non-leaf nodes are.</Paragraph>
    <Paragraph position="2"> macro-acts (e.g., &amp;quot;disjunction&amp;quot; or &amp;quot;sequence&amp;quot; of dialogue acts) and leaf nodes are dialogue acts (see \[Sadek 91\]).</Paragraph>
    <Paragraph position="3"> A dialogue act conveys information about its type (e.g., &amp;quot;inform&amp;quot;, &amp;quot;yn-question&amp;quot; or &amp;quot;confirm&amp;quot;), its propositional content (i.e., a semantico-conceptual representation of the information to be communicated), and the interlocutors.</Paragraph>
    <Paragraph position="4"> The surface linguistic act planner transforms a plan of dialogue acts into a plan of surface linguistic acts (i.e., the message). In particular, the dialogue act type is transformed into a surface linguistic act type such as &amp;quot;assertion&amp;quot;, &amp;quot;answer&amp;quot; or &amp;quot;question&amp;quot;, and the semantico-conceptual content into a semantic propositional content (cf. figure 1 and section 3).</Paragraph>
    <Paragraph position="5"> One of the problems which appear in traditional generation systems concerns the message itself: it is under-specified with respect to the language. On the one hand, the message planner cannot influence the way in which the message will be verbalized, and, on the other hand, the message is not detailed enough for the many possibilities for its expression to be controlled. Figure 1 shows several messages (a text plan and three surface linguistic acts corresponding to the same dialogue act) and their different verbalizations.</Paragraph>
    <Paragraph position="6"> A second problem is related to the fact that most generation systems produce texts successfully since they implicitly ensure that the messages are expressible. For instance, in the case where the message is a text plan, each atomic unit in the message must be a proposition, and thus can always be realized as a clause. Each unit can be independently translated into the language using the linguistic realization component, since there are  * Content 1 = a destination-event whose theme is &amp;quot;the 10:00 flight&amp;quot; and destination is &amp;quot;3FK&amp;quot;: (BA1) The lO:OO flight goes to JFK.</Paragraph>
    <Paragraph position="7"> (BA2) It goes to JFK.</Paragraph>
    <Paragraph position="8"> .(BA3) To JFK.</Paragraph>
    <Paragraph position="9"> * Content 2 -- an identity between &amp;quot;the arrival airport of the 10:00 flight&amp;quot; and &amp;quot;JFK&amp;quot;: (Bin) The arrival airport of the 10:00 flight is JFK.</Paragraph>
    <Paragraph position="10"> (BB2) The arrival airport is JFK.</Paragraph>
    <Paragraph position="11"> (BB3) JFK.</Paragraph>
    <Paragraph position="12"> * Content 3 = a destination-event whose theme is &amp;quot;the hearer&amp;quot; and destination is &amp;quot;JFK&amp;quot;: (Bca) You will arrive at JFK.</Paragraph>
    <Paragraph position="13"> (Be2) At JFh'.</Paragraph>
    <Paragraph position="14">  few restrictions on how to connect clauses. In particular, clauses can be connected with coordinate or subordinate conjunctions or can be simply realized as separate sentences. However, this kind of approach does not use the full expressive power of the language in which units may be much more tightly composed. Moreover, as argued in \[Hovy 92\], a two-component generation system is not satisfactory in producing 'good quality' texts since too many phenomena are ignored or processed in a simplistic way, for example, anaphora planning, choice of lexical items, aggregation of clauses and noun phrases, selection of grammatical constructions (e.g., the choice of the verb voice), and segmentation into sentences (i.e., single sentence vs. separate sentences, hypotaxis vs. parataxis, and determination of clause order). The main difficulty in taking these phenomena into account is due to the fact that they are &amp;quot;supra-grammatical but not really related to content selection and organization&amp;quot; \[Hovy 92, p. 2\]. In fact, Hovy argues that these phenomena should be treated after the message planning and before the linguistic realization.</Paragraph>
    <Paragraph position="15"> A third problem is related to the fact that in a two-component generation system the conceptual decisions are taken by the message planner and the the linguistic decisions by the realization component. Since conceptual and linguistic decisions are dependent on each other (see \[Danlos 87\]), the two components should be able to communicate with each other. On the one hand, the definition of such a communication is a complex task, due to the gap between the two activities (see \[Meteer 92\]). On the other hand, all the grammatical details that can be provided by a linguistic realizer may not be useful to take these decisions. We think that, in a first step, it is use- null ful to know that such linguistic phenomena exist in the target language without being able to realize them. For example, it is useful to know that a present participial clause can verbalize the rhetorical relation &amp;quot;result&amp;quot;, but it is not useful to know (in a first step) that a present participial clause is formed by adding &amp;quot;ing&amp;quot; at the end of the stem of a verb.</Paragraph>
  </Section>
class="xml-element"></Paper>